An Approach Based on Bayesian Network for Improving ProjectManagement Maturity: An Application to Reduce Cost Overrun Risksin Engineering Projects
رویکرد مبتنی بر شبکه بیزی برای بهبود بلوغ مدیریت پروژه: برنامه ای برای کاهش هزینه های پیشی گرفتن از پروژه های مهندسی ریسکین-2020
The project management field has the imperative to increase the success probability of projects. Expertshave developed several Project Management Maturity (PMM) models to assess project managementpractices and improve the project outcome. However, the current literature lacks models that allowexperts to correlate the measured maturity with the expected probability of success. The present paperdevelops a general framework and a method to estimate the impact of PMM on project performance. Ituses Bayesian networks to formalize project management experts’ knowledge and to extract knowledgefrom a database of past projects. An industrial case concerning large projects in the oil and gas industryis used to illustrate the application of the method to reduce the risk of project cost (or budget) overruns.
Keywords:Bayesian Networks | Cost Overrun | Knowledge Modeling | Maturity Model | Project Management
Bayesian networks + reinforcement learning: Controlling group emotion from sensory stimuli
شبکه های بیزی + یادگیری تقویتی : کنترل احساسات گروهی از محرک های حسی-2020
As communication technology develops, various sensory stimuli can be collected in service spaces. To enhance the service effectiveness, it is important to determine the optimal stimuli to induce group emo- tion in the service space to the target emotion. In this paper, we propose a stimuli control system to adjust the group emotion. It is a stand-alone system that can determine optimal stimuli by utility ta- ble and modular tree-structured Bayesian networks designed for emotion prediction model proposed in the previous study. To verify the proposed system, we collected data using several scenarios at a kinder- garten and a senior welfare center. Each space is equipped with sensors for collection and equipment for controlling stimuli. As a result, the system shows a performance of 78% in the kindergarten and 80% in the senior welfare center. The proposed method shows much better performance than other classifica- tion methods with lower complexity. Also, reinforcement learning is applied to improving the accuracy of stimuli decision for a positive effect on system performance.
Keywords: Adjusting emotion | Group emotion | Bayesian networks | Reinforcement Learning | IoT
A knowledge-based reasoning model for crime reconstruction and investigation
یک مدل استدلال دانش بنیان برای بازسازی و تحقیقات جرم-2020
Artificial intelligence has been successfully applied in many areas including forensic sciences. Perhaps all forensic works can be regarded as helping reconstruct crimes, i.e. clarify and sequence the events that took place in the commission of a crime through evidence. However, there are few researches on the crime reconstruction using artificial intelligence methods. In this paper, we present a model based on Bayesian networks to help solve crimes. The model, which is termed ‘case-type based model’, is based on the knowledge of a type of crimes. We use Bayesian networks to represent the knowledge and conduct the uncertainty reasoning. We propose a growth algorithm of Bayesian networks to adapt the model to different cases. The model was tested through a real case, and the results indicate that the model can provide effective investigation suggestions and achieve the crime reconstruction.
Keywords: Artificial intelligence | Forensic science | Bayesian networks | Criminal investigation | Uncertainty reasoning | Evidence
A novel approach to solve AI planning problems in graph transformations
یک رویکرد جدید برای حل مشکلات برنامه ریزی هوش مصنوعی در تحولات نمودار-2020
The aim of AI planning is to solve the problems with no exact solution available. These problems usually have a big search space, and planning may not find plans with the least actions and in the shortest time. Recent researches show that using suitable heuristics can help to find desired plans. In planning problems specified formally through graph transformation system (GTS), there are dependencies between applied rules (actions) in the search space. This fact motivates us to solve the planning problem for a small goal (instead of the main goal), extract dependencies from the searched space, and use these dependencies to solve the planning problem for the main goal. In GTS based systems, the nodes of a state (really is a graph) can be grouped due to their type. To create a small (refined) goal, we use a refinement technique to remove the predefined percent of nodes from each group of the main goal. Bayesian Optimization Algorithm (BOA) is then used to solve the planning problem for the refined goal. BOA is an Estimation of Distribution Algorithm (EDA) in which Bayesian networks are used to evolve the solution populations. Actually, a Bayesian network is learned from the current population, and then this network is employed to generate the next population. Since the last Bayesian network learned in BOA has the knowledge about dependencies between applied rules, this network can be used to solve the planning problem for the main goal. Experimental results on four well-known planning domains confirm that the proposed approach finds plans with the least actions and in the lower time compared with the state-of-the-art approaches.
Keywords: Bayesian Optimization Algorithm | AI planning | Graph transformation system | Bayesian network | Refinement
Customized risk assessment in military shipbuilding
ارزیابی ریسک سفارشی در کشتی سازی ارتش-2020
This paper describes a customized risk assessment framework to be applied in military shipbuilding projects. The framework incorporates the Delphi method with visual diagrams, Bayesian Networks (BN) and the expression of expert opinions through linguistic variables. Noisy-OR and Leak Canonical models are used to determine the conditional probabilities of the BN model. The approach can easily be adapted for other shipbuilding construction projects. The visual diagrams that support the Delphi questionnaire favor the comprehensive visualization of the interdependencies between risks, causes, risks and causes, and risks and effects. The applicability of the framework is illustrated through the assessment of risk of two real military shipbuilding projects. This assessment includes a sensitivity analysis that is useful to prioritize mitigation actions. In the two cases studies, the risks with higher probability of occurrence were failures or errors in production, of the contracted, in the requirements, and in planning. The results of the sensitivity analysis showed that a set of mitigation actions directed at relatively easily controllable causes would have achieved important reductions in risk probabilities
Keywords: Project management | Shipbuilding projects | Risk network model | Delph | iBayesian network
Bayesian networks and dissonant items of evidence: A case study
شبکه های بیزی و شواهد متفرق: یک مطالعه موردی-2020
The assessment of different items of evidence is a challenging process in forensic science, particularly when the relevant elements support different inferential directions. In this study, a model is developed to assess the joint probative value of three different analyses related to some biological material retrieved on an object of interest in a criminal case. The study shows the ability of probabilistic graphical models, say Bayesian networks, to deal with complex situations, those that one expects to face in real cases. The results obtained by the model show the importance of a conflict measure as an indication of inconsistencies in the model itself. A contamination event alleged by the defense is also introduced in the model to explain and solve the conflict. The study aims to give an insight in the application of a probabilistic model to real criminal cases.
Keywords: DNA evidence | Activity level interpretation | Bayesian networks | Conflict measure
Analytical games for knowledge engineering of expert systems in support to Situational Awareness: The Reliability Game case study
بازی های تحلیلی برای مهندسی دانش سیستم های خبره در حمایت از آگاهی وضعیتی: مطالعه موردی بازی اطمینان-2019
Knowledge Acquisition (KA) methods are of paramount importance in the design of intelligent systems. Research is ongoing to improve their effectiveness and efficiency. Analytical games appear to be a promis- ing tool to support KA. In fact, in this paper we describe how analytical games could be used for Knowl- edge Engineering of Bayesian networks, through the presentation of the case study of the Reliability Game. This game has been developed with the aim of collecting data on the impact of meta-knowledge about sources of information upon human Situational Assessment in a maritime context. In this paper we describe the computational model obtained from the dataset and how the card positions, which reflect a player belief, can be easily converted in subjective probabilities and used to learn latent constructs, such as the source reliability, by applying the Expectation-Maximisation algorithm.
Keywords: Source reliability | Expert knowledge | Knowledge acquisition | Bayesian networks | Parameter learning | Analytical game
An ontology-based methodology for hazard identification and causation analysis
یک روش مبتنی بر هستی شناسی برای شناسایی ریسک و تجزیه و تحلیل علیت-2019
This article presents a dynamic hazard identification methodology founded on an ontology-based knowl-edge modeling framework coupled with probabilistic assessment. The objective is to develop an efficientand effective knowledge-based tool for process industries to screen hazards and conduct rapid risk esti-mation. The proposed generic model can translate an undesired process event (state of the process)into a graphical model, demonstrating potential pathways to the process event, linking causation tothe transition of states. The Semantic web-based Web Ontology Language (OWL) is used to captureknowledge about unwanted process events. The resulting knowledge model is then transformed intoProbabilistic-OWL (PR-OWL) based Multi-Entity Bayesian Network (MEBN). Upon queries, the MEBNsproduce Situation Specific Bayesian Networks (SSBN) to identify hazards and their pathways along withprobabilities. Two open-source software programs, Protégé and UnBBayes, are used. The developed modelis validated against 45 industrial accidental events extracted from the U.S. Chemical Safety Board’s (CSB)database. The model is further extended to conduct causality analysis.
Keywords:Hazard identification |Probabilistic ontology |Web ontology language | Multi-entity Bayesian network | Expert system
The AXIOM approach for probabilistic and causal modeling with expert elicited inputs
رویکرد AXIOM برای مدل سازی احتمالی و علی با ورودی های خبره-2019
Expert informants can be used as the principal information source in the modeling of socio-techno-economic systems or problems to support planning, foresight and decision-making. Such modeling is theory-driven, grounded in expert judgment and understanding, and can be contrasted with data-driven modeling approaches. Several families of approaches exist to enable expert elicited systems modeling with varying input information requirements and analytical ambitions. This paper proposes a novel modeling language and computational process, which combines aspects from various other approaches in an attempt to create a flexible and practical systems modeling approach based on expert elicitation. It is intended to have high fitness in modeling of systems that lack statistical data and exhibit low quantifiability of important system characteristics. AXIOM is positioned against Bayesian networks, crossimpact analysis, structural analysis, and morphological analysis. The modeling language and computational process are illustrated with a small example model. A software implementation is also present
Keywords: Systems modeling | Modeling techniques | Decision support | Cross-impact analysis | Belief networks | Expert elicitation
Knowledge representation using non-parametric Bayesian networks for tunneling risk analysis
نمایش دانش با استفاده از شبکه های بیزی غیر پارامتری برای تجزیه و تحلیل ریسک تونل زنی-2019
Knowledge capture and reuse are critical in the risk management of tunneling works. Bayesian networks (BNs) are promising for knowledge representation due to their ability to integrate domain knowledge, encode causal relationships, and update models when evidence is available. However, the model development based on classic BNs is challenging when expert opinions are solicited due to the discretization of variables and quantification of large conditional probability tables. This study applies non-parametric BNs, which only require the elicitation of the marginal distribution corresponding to each node and correlation coefficient associated with each edge, to develop a knowledge-based expert system for tunneling risk analysis. In particular, we propose to use the pairwise Pearsons linear correlations to parameterize the model because the assessment is intuitive and experts in the engineering domain are more familiar and comfortable with this notion. However, when Spearmans rank correlation is given, the method can also be used by modification of the marginals. The method is illustrated with a tunnel case in the Wuhan metro project. The expert knowledge of risk assessment for common failures in shield tunneling is integrated and visualized. The developed model is validated by real documented accidents. Potential applications of the model are also explored, such as decision support for risk-based design.
Keywords: Non-parametric Bayesian networks | Structured expert judgment | Expert system | Risk analysis | Tunneling